Research of Speech Recognition for Detection of Program Behavior Based on CDHMM

摘要：

In order to reduce the error in the detection of speech recognition, improve the correct rate of speech recognition.This paper presents one improvement method of speech recognition program behavior detection based on continuous hidden Markov model (CDHMM). Through a simplified, deal with multidimensional discrete speech symbol program behavior detection method, making the continuous hidden Markov model can receive variety of different characteristic sequences at the same time. The problem of that speech authentication system recognition rate declining with time is resolved. Experiments show that the method reduces rejection rate and improves speech recognition systems adaptability.

关键词： CDHMM Speech Recognition HMM Behavior Detection

作者: Zhangyong Long Hanyu Lu

作者单位: College of Communication Signals Nanjing Institute of Railway Technology Nanjing ,210015, China Department of Information Engineering Guizhou University Guiyang 550003, China

会议类型: 国际会议

会议名称: 2012 International Conference on Electric Technology and Civil Engineering(2012 电子技术与土木工程国际会议 ICETCE 2012)

会议地点: 三峡

会议语种:英文

页码: 930-933

在线出版日期: 2012-05-18（万方平台首次上网日期，不代表论文的发表时间）